aufklarer/EmbeddingGemma-300M-MLX-8bit
sentence-similarity model by aufklarer
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
MLX conversion of google/embeddinggemma-300m for on-device transcript search on Apple Silicon. It produces the checkpoint's own 768-dimensional sentence embeddings: prompt, bidirectional Gemma 3 encoder, mean pooling, dense head, L2 normalization. Exported from the upstream checkpoint at revision 57c266a740f537b4dc058e1b0cda161fd15afa75, not from a third-party MLX conversion. Used by speech-runtime's TextEmbedding module: A query and the documents that answer it are embedded under different prompts, which embed(query:) and embed(documents:) apply. 3 attention heads over 1 key/value head, head dimension 256 task: search result | query: for a query Cosine against the float32 source through sentence-transformers, on identical token ids, over 240 meeting-transcript passages and 800 utterances: 0.9989 minimum, 0.9996 mean. Three details decide whether a port reproduces this model, and each was measured against the source: tokens fewer than 257 positions away, which is what transformers derives from the stored slidingwindow: 512 for a bidirectional Gemma 3. It is…
Read the full model card ↗ · Preview checked 2026-10-30T22:35:10.337Z
Inside the original model card — Document outline
- EmbeddingGemma 300M — MLX 8-bit
- Usage (Swift / MLX)
- Model details
- Fidelity
- What a runtime has to match
- Conversion
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: gemma. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
aufklarer/EmbeddingGemma-300M-MLX-8bit is a sentence-similarity model repository published by aufklarer on Hugging Face. The source reports the mlx library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- sentence-similarity
- Library
- mlx
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 307,581,696
- Architecture
- Not reported
- License
- gemma
- Access
- Not gated by Hugging Face
- Created
- 2026-09-16T06:27:58.000Z
- Last modified
- 2026-09-16T06:28:17.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: google/embeddinggemma-300m
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-16T06:34:51.485Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
sentence-transformers/all-MiniLM-L6-v2
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
sentence-transformers/all-mpnet-base-v2